Predicting jaywalking behaviors of vulnerable road users

2. The method of claim 1, comprising assigning a current heading of the VRU as the nominal heading of the VRU.

6. The method of claim 5, wherein the system is configured not to generate a predicted heading offset for the VRU in response to the jaywalking prediction indicating that the VRU is not jaywalking and is not likely to jaywalk on the roadway traveled by the vehicle.

8. The method of claim 7, wherein the jaywalking prediction model comprises a decision tree, a random decision forest, an artificial neural network, or a regression model.

9. The method of claim 1, wherein the plurality of environmental features include at least one of a road edge, a lane boundary, a sidewalk, a bicycle lane, a road curb, or an intersection.

10. The method of claim 1, wherein the VRU is a pedestrian, a cyclist, or a low-speed motorized vehicle.

11. The method of claim 1, wherein the vehicle is a fully autonomous or semi-autonomous vehicle.

13. The method of claim 1, wherein the heading estimation model is a machine-learning model that was trained using a supervised machine-learning technique.

14. The method of claim 1, wherein the physical relationship between the VRU and a first environmental feature of the plurality of environmental features, as indicated by a first predictive input of the set of predictive inputs, comprises at least one of a positional relationship, a distal relationship, or an angular relationship between the VRU and the first environmental feature.

15. The method of claim 1, comprising generating a predicted heading of the VRU by adding the predicted heading offset for the VRU to the nominal heading of the VRU.

16. The method of claim 1, comprising selecting a location of a point along a first environmental feature of the plurality of environmental features, wherein determining the nominal heading of the VRU comprises determining a direction of a vector from the current location of the VRU to the location of the selected point along the first environmental feature.

17. The method of claim 16, wherein the first environmental feature is a road edge and selecting the location of the point along the first environmental feature comprises selecting a location of the road edge that is closest to the current location of the VRU.